---
id: "contrarian-prompts-dont-compound"
type: "contrarian-insight"
source_timestamps: ["08:28:00", "08:57:00"]
tags: ["prompt-engineering"]
related: ["concept-skills-vs-prompts", "claim-skills-compound", "quote-skills-compound"]
challenges: "The conventional view that mastering 'prompt engineering' (writing complex, monolithic text blocks) is the ultimate goal of interacting with LLMs."
sources: ["s43-file-format-agreement"]
sourceVaultSlug: "s43-file-format-agreement"
originDay: 43
---
# Prompts are static; skills compound

## Contrarian Position

Mastering *prompt engineering* — writing ever-more-elaborate monolithic text blocks — is **not** the ultimate goal of interacting with LLMs. The terminal form is **skill engineering**.

## What It Challenges

The conventional view (still dominant in 2024 content) that the highest-leverage AI skill is crafting clever multi-paragraph prompts.

## Speaker's Argument

Prompts are ephemeral and don't compound; skills are persistent, version-controlled, and testable — see [[concept-skills-vs-prompts]] and [[claim-skills-compound]].

## Steelman of the Conventional View

Proponents argue that **all skills are just prompts with YAML** and that the new vocabulary masks the underlying continuity. The compounding is real but partial.

## Where the Speaker's Position Wins

In agent-first systems where invocation count is huge and human supervision is sparse, the *file-shaped artifact* changes incentives. You **invest** in a skill the way you'd invest in a function library — something you'd rarely do with a prompt.